From dev-return-2274-archive-asf-public=cust-asf.ponee.io@singa.incubator.apache.org Fri Aug 24 04:59:04 2018 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx-eu-01.ponee.io (Postfix) with SMTP id 2A25B180677 for ; Fri, 24 Aug 2018 04:59:04 +0200 (CEST) Received: (qmail 99092 invoked by uid 500); 24 Aug 2018 02:59:03 -0000 Mailing-List: contact dev-help@singa.incubator.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@singa.incubator.apache.org Delivered-To: mailing list dev@singa.incubator.apache.org Received: (qmail 98824 invoked by uid 99); 24 Aug 2018 02:59:03 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd1-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 24 Aug 2018 02:59:03 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd1-us-west.apache.org (ASF Mail Server at spamd1-us-west.apache.org) with ESMTP id C7B07C76DE for ; Fri, 24 Aug 2018 02:59:02 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd1-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: -110.301 X-Spam-Level: X-Spam-Status: No, score=-110.301 tagged_above=-999 required=6.31 tests=[ENV_AND_HDR_SPF_MATCH=-0.5, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, USER_IN_DEF_SPF_WL=-7.5, USER_IN_WHITELIST=-100] autolearn=disabled Received: from mx1-lw-us.apache.org ([10.40.0.8]) by localhost (spamd1-us-west.apache.org [10.40.0.7]) (amavisd-new, port 10024) with ESMTP id DzYL3JgZ2HqR for ; Fri, 24 Aug 2018 02:59:02 +0000 (UTC) Received: from mailrelay1-us-west.apache.org (mailrelay1-us-west.apache.org [209.188.14.139]) by mx1-lw-us.apache.org (ASF Mail Server at mx1-lw-us.apache.org) with ESMTP id 2B83D5F27D for ; Fri, 24 Aug 2018 02:59:02 +0000 (UTC) Received: from jira-lw-us.apache.org (unknown [207.244.88.139]) by mailrelay1-us-west.apache.org (ASF Mail Server at mailrelay1-us-west.apache.org) with ESMTP id 702BBE2618 for ; Fri, 24 Aug 2018 02:59:01 +0000 (UTC) Received: from jira-lw-us.apache.org (localhost [127.0.0.1]) by jira-lw-us.apache.org (ASF Mail Server at jira-lw-us.apache.org) with ESMTP id A8C07246C3 for ; Fri, 24 Aug 2018 02:59:00 +0000 (UTC) Date: Fri, 24 Aug 2018 02:59:00 +0000 (UTC) From: "ASF subversion and git services (JIRA)" To: dev@singa.incubator.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Commented] (SINGA-383) Add Separable Convolution for autograd MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 [ https://issues.apache.org/jira/browse/SINGA-383?page=3Dcom.atlassian.= jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D16591= 086#comment-16591086 ]=20 ASF subversion and git services commented on SINGA-383: ------------------------------------------------------- Commit ca70bdf3f02412f216d10e8d4ba6c265bdd139ee in incubator-singa's branch= refs/heads/master from xuewanqi [ https://git-wip-us.apache.org/repos/asf?p=3Dincubator-singa.git;h=3Dca70b= df ] SINGA-383 Add Separable Convolution for autograd - let Conv2d layer support 'groups' paramters, for grouped convolution. - implement Separable Convolution layer. - add unit test case for new developed SeparableConv2d layer. - the implemented SeparableConv2d layer has passed both unit test and netwo= rk test. > Add Separable Convolution for autograd > -------------------------------------- > > Key: SINGA-383 > URL: https://issues.apache.org/jira/browse/SINGA-383 > Project: Singa > Issue Type: New Feature > Reporter: wangwei > Priority: Major > > This type of convolution is used in [Xception model|https://arxiv.org/pdf= /1610.02357.pdf] and is supported by [other libraries|[https://github.com/p= ytorch/pytorch/issues/1708].] > =C2=A0 > To implement it in Singa, we create a new operation (separable_conv_2d) b= y calling a depthwise_conv_2d (normal convolution with number of output cha= nnels=3D1, and number of groups =3D number of input channels); and then cal= ling normal convolution with number of groups=3D1, and kernel size=3D1, i.e= . pointwise convolution. -- This message was sent by Atlassian JIRA (v7.6.3#76005)